In this study, the altitude and yaw angle tracking is considered for a scale model helicopter, mounted on an experimental platform, in the presence of model uncertainties, which may be caused by unmodelled dynamics, or aerodynamical disturbances from the environment. To deal with the uncertainties, approximation-based techniques using neural network (NN) are proposed. In particular, two different types of NN, namely multilayer neural network and radial basis function neural network are adopted in control design and stability analysis. Based on Lyapunov synthesis, the proposed adaptive NN control ensures that both the altitude and the yaw angle track the given bounded reference signals to a small neighbourhood of zero, and guarantees semiglobal uniform ultimate boundedness of all the closed-loop signals at the same time. The effectiveness of the proposed control is illustrated through extensive simulations. Compared with the model-based control, approximation-based control yields better tracking performance in the presence of model uncertainties.